Research and improvement on algorithm of image feature point matching

The paper focuses on the improvement by giving consideration to density degree of featured points´, after carefully scrutinizing on feature matching algorithm, along with the former way to examine the similarity degree of featured points´. We decrease the threshold of correlation degree of corners, to avoid the unsuccessful matching by the unsuitable threshold setting. It is through the experiment comparison in the latter chapter have we arrived to the conclusion that the algorithm is less time-consuming (decreased by 49.2%) and the nicety is improved greatly (increased by 20%).